Next to stroke, the epilepsy is one of the most serious neurological disorders. Due to the hyperactive firing of neurons on a cellular level, epilepsy is caused. The activities of the cortical regions are recorded with the help of Electroencephalogram (EEG) which helps in the diagnosis of epilepsy. The normal patterns of the activities of neurons becomes severely disturbed in the case of epilepsy, thereby causing several hazardous consequences to the patients. The recordings of the EEG are quite long and so with the help of Hilbert Transform the dimensions of the EEG signals are reduced. Now with the help of Elman Backpropagation and Multilayer Perceptron (MLP) Neural Networks, the dimensionally reduced values through Hilbert Transform are classified for assessing the epilepsy risk levels from EEG signals. The result analysis show an average accuracy of about 100% is obtained when the combination of Hilbert transform with Elman Backpropagation neural network is used. Similarly when Hilbert transform is implemented with the help of MLP, an average accuracy of about 97.916% along with a Performance Index of 95.74% is obtained.
Hilbert transform with Elman backpropagation and multilayer perceptrons for epilepsy classification
2017-04-01
283118 byte
Conference paper
Electronic Resource
English
Classification by Autoassociative Multilayer Perceptrons
British Library Conference Proceedings | 1994
|Parallel Off-Line Training of Multilayer Perceptrons
British Library Conference Proceedings | 1995
|Optimizing Digital Hardware Perceptrons for Multi-Spectral Image Classification
British Library Online Contents | 2003
|Realization of a Multilayer Backpropagation Neural Network with Parallel Working Microprocessors
British Library Conference Proceedings | 1994
|